HTTP SSE (Server-Sent Events) Access

To provide broader compatibility and a more convenient access method, the Bitseek Chat gateway also supports streaming calls via the HTTP SSE (Server-Sent Events) protocol.

This interface is designed to be fully compatible with OpenAI's Chat Completions API. This means you can use any OpenAI-compatible client library (such as the official openai libraries for Python and Node.js) to connect easily by pointing the base_url (or baseURL) to our service address.

Endpoint

• URL: https://chat-proxy.bitseek.ai/v1/chat/completions
• Method: POST
• Headers:
  • Content-Type: application/json
  • Accept: text/event-stream
  • Authorization: Bearer YOUR_API_KEY

Request Body

The request body follows OpenAI's chat/completions format. You must set the stream parameter to true.

Example:

{
    "messages": [
        {
            "role": "user",
            "content": "Hello, please introduce yourself."
        }
    ],
    "stream": true
}

Client Examples

Python

This example shows how to call the service using the official openai Python library.

1. Installation:

pip install openai

2. Code:

from openai import OpenAI

# 1. Initialize the client
# Point the base_url to the Bitseek Chat service address
# Use your authentication key for api_key
client = OpenAI(
    base_url="https://chat-proxy.bitseek.ai/v1",
    api_key="YOUR_API_KEY"
)

# 2. Make a streaming request
# Set the stream parameter to True
stream = client.chat.completions.create(
    messages=[{"role": "user", "content": "Write a short poem about the starry sky"}],
    stream= true
)

# 3. Process the streaming response
# Iterate through the event stream and print the content
print("AI: ", end="")
for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

print() # Newline at the end

Node.js

This example shows how to call the service using the official openai Node.js library.

1. Installation:

npm install openai

2. Code:

import OpenAI from "openai";

// 1. Initialize the client
// Point the baseURL to the Bitseek Chat service address
// Use your authentication key for apiKey
const client = new OpenAI({
    baseURL: "https://chat-proxy.bitseek.ai/v1",
    apiKey: "YOUR_API_KEY",
});

async function main() {
    // 2. Make a streaming request
    // Set the stream parameter to true
    const stream = await client.chat.completions.create({
        messages: [
            {
                role: "user",
                content: "Write a short poem about the starry sky",
            },
        ],
        stream: true,
    });

    // 3. Process the streaming response
    // Iterate through the event stream and print the content
    process.stdout.write("AI: ");
    for await (const chunk of stream) {
        process.stdout.write(chunk.choices[0]?.delta?.content || "");
    }
    process.stdout.write("\n"); // Newline at the end
}

main();

Java

This example uses the popular openai-java library by Theo Kanning.

1. Dependency (Maven): Add this to your pom.xml:

<dependency>
    <groupId>com.theokanning.openai-gpt3-java</groupId>
    <artifactId>service</artifactId>
    <version>0.18.2</version>
</dependency>

2. Code:

import com.theokanning.openai.completion.chat.ChatCompletionRequest;
import com.theokanning.openai.completion.chat.ChatMessage;
import com.theokanning.openai.service.OpenAiService;
import java.time.Duration;
import java.util.List;

class SseExample {
    public static void main(String[] args) {
        // 1. Initialize the service
        // Use your authentication key for the token.
        // Customize the base URL to point to the Bitseek Chat service.
        // Note: The base URL should NOT include the /v1 path for this library.
        String token = "YOUR_API_KEY";
        String baseUrl = "https://your-api-domain.com";
        OpenAiService service = new OpenAiService(token, baseUrl, Duration.ofSeconds(60));

        // 2. Create a streaming request
        // Set stream to true to enable SSE.
        ChatCompletionRequest request = ChatCompletionRequest.builder()
                .model("your-model-name")
                .messages(List.of(new ChatMessage("user", "Write a short poem about the starry sky")))
                .stream(true)
                .build();

        // 3. Process the streaming response
        // The streamChatCompletion method returns a Flowable that emits events.
        // We block and print each chunk's content to the console.
        System.out.print("AI: ");
        service.streamChatCompletion(request)
                .blockingForEach(chunk -> {
                    chunk.getChoices().forEach(choice -> {
                        String content = choice.getMessage().getContent();
                        if (content != null) {
                            System.out.print(content);
                        }
                    });
                });

        System.out.println(); // Newline at the end
        service.shutdownExecutor();
    }
}

General Code Explanation

• base_url / baseURL: This is the most critical parameter. You must set it to the API address provided by Bitseek Chat. Note the path differences required by different libraries (/v1 for Python/Node.js, no path for the Java library).
• api_key / token: Provide your valid API key for authentication.
• stream: true: This flag enables the SSE streaming response.
• chunk: Each chunk object received from the stream is consistent with the OpenAI SDK's ChatCompletionChunk structure, allowing you to easily extract incremental content.

Data Stream Format

Each event returned by the server is a data: field containing an OpenAI-compatible JSON string. The stream is terminated by a special data: [DONE] event. The client libraries handle the parsing of these events automatically.